用血管特征提升OCTA检测老年黄斑变性的精度
Vessel-Aware Deep Learning for OCTA-Based Detection of AMD
- 引入血管特异性注意力机制，融合扭曲度与灌注缺失图
- 毛细血管缺失图在大尺度平滑下表现最佳，动脉扭曲度最稳定
- 结果可解释，符合黄斑变性病理机制，适合临床医生参考
年龄相关性黄斑变性（AMD）早期表现为微血管改变，可通过光学相干断层扫描血管成像（OCTA）无创捕捉。现有深度学习模型多依赖全局特征，忽略具有临床意义的血管生物标志物。本文提出一种外部乘性注意力框架，利用动脉、静脉和毛细血管分割生成的血管扭曲度图与灌注缺失图，通过多尺度平滑突出血管重构和毛细血管稀疏的连贯模式。扭曲度反映血管几何异常，与自身调节功能障碍相关；灌注缺失图捕捉结构性视网膜损伤前的局部血流不足。这些生物标志物图与OCTA投影融合，引导深度分类器关注生理相关区域。结果显示，动脉扭曲度具有一致的判别能力，而毛细血管缺失图在密度类指标中表现最优，尤其在较大平滑尺度下。该方法提供与已知AMD病理生理一致的可解释性洞察。
原文摘要 · Abstract (English)
Age-related macular degeneration (AMD) is characterized by early micro-vascular alterations that can be captured non-invasively using optical coherence tomography angiography (OCTA), yet most deep learning (DL) models rely on global features and fail to exploit clinically meaningful vascular biomarkers. We introduce an external multiplicative attention framework that incorporates vessel-specific tortuosity maps and vasculature dropout maps derived from arteries, veins, and capillaries. These biomarker maps are generated from vessel segmentations and smoothed across multiple spatial scales to highlight coherent patterns of vascular remodeling and capillary rarefaction. Tortuosity reflects abnormalities in vessel geometry linked to impaired auto-regulation, while dropout maps capture localized perfusion deficits that precede structural retinal damage. The maps are fused with the OCTA projection to guide a deep classifier toward physiologically relevant regions. Arterial tortuosity provided the most consistent discriminative value, while capillary dropout maps performed best among density-based variants, especially at larger smoothing scales. Our proposed method offers interpretable insights aligned with known AMD pathophysiology.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。